iccv iccv2013 iccv2013-392 iccv2013-392-reference knowledge-graph by maker-knowledge-mining

392 iccv-2013-Similarity Metric Learning for Face Recognition


Source: pdf

Author: Qiong Cao, Yiming Ying, Peng Li

Abstract: Recently, there is a considerable amount of efforts devoted to the problem of unconstrained face verification, where the task is to predict whether pairs of images are from the same person or not. This problem is challenging and difficult due to the large variations in face images. In this paper, we develop a novel regularization framework to learn similarity metrics for unconstrained face verification. We formulate its objective function by incorporating the robustness to the large intra-personal variations and the discriminative power of novel similarity metrics. In addition, our formulation is a convex optimization problem which guarantees the existence of its global solution. Experiments show that our proposed method achieves the state-of-the-art results on the challenging Labeled Faces in the Wild (LFW) database [10].


reference text

[1] A. Beck and M. Teboulle. A fast iterative shrinkagethresholding algorithm for linear inverse problems. SIAM J. on Imaging Sciences, 2009.

[2] P. N. Belhumeur, J. Hespanda and D. Kiregeman. Eigenfaces vs Fisherfaces: recognition using class specific linear projection. IEEE Trans. PAMI, 19: 711–720, 1997.

[3] G. Chechik, V. Sharma, U. Shalit, and S. Bengio. Large scale online learning of image similarity through ranking. J. of Machine Learning Research, 11: 1109–1 135, 2010.

[4] D. Chen, X. Cao, L. Wang, F. Wen, and J. Sun. Bayesian face revisited: A joint formulation. ECCV, 2012.

[5] S. Chopra, R. Hadsell, and Y. LeCun. Learning a similarity metric discriminatively with application to face verification. CVPR, 2005.

[6] Z. Cui, W. Li, D. Xu, S. Shan, and X. Chen. Fusing robust face region descriptors via multiple metric learning for face recognition in the wild. CVPR, 2013.

[7] J. Davis, B. Kulis, P. Jain, S. Sra, and I. Dhillon. Informationtheoretic metric learning. ICML, 2007.

[8] M. Guillaumin, J. Verbeek and C. Schmid. Is that you? Metric learning approaches for face identification. ICCV, 2009. 22441144 Methods100015002000 Table4:PrfomancefdISL TuDifMb -eLISrTeDM[7n L]8t mer0i .c87 5l1e9864a732r8n± in0g .0 m0 e4371t84hods0 v.8e7 6r921s45 u2075s± th0 e .0 n0u452m9 6ber0o .f8 76i32m90168372ag± e-0p .a0 i 0r453s 6 p5erfoldintheursicted setting of LFW. MethodAccuracy SSIIFFTT L PMLDNAN,, f fuunnnneelleedd [ [1272]]00..886025 ± ± 0 0..00152 SSIIFFTT L SuDbM-SLM, fLun, fnuenlneedle [8d]0.08.683422 ± ± 0 0..00040046 L BLPB P mPuSLlutiDbsA-hSo,Mt aLlaig,lngaelndige[nd1e[72d0] 0 . 8 75 31 537± ±0 . 0 0 56 15 CSoumbC-SionmLcMeoDLdbmiMnPbcoeLinmd-DeMbdmAiukJn,flNoetiuNdns,thnfoeBufltne,a ydnleis&lgeinadne;&lid;[g84n[a]2el0idg]n[1e7d]0 .9 80795 0 7± ±0 0. 0 01654 108 Table 5: Comparison of Sub-SML with other state-of-the-art results in the unrestricted setting of LFW: the top 7 rows are based on single descriptor and the bottom 4 rows are based on multiple descriptors.

[9] B. Hariharan, J. Malik, and D. Ramanan. Discriminative decorrelation for clustering and classi?cation. ECCV, 2012.

[10] Gary B. Huang, Manu Ramesh, Tamara Berg, and Erik Learned-Miller. Labeled Faces in the Wild: A Database for Studying Face Recognition in Unconstrained Environments. ECCV, 2008.

[11] M. Kan, S. Shan, D. Xu, and X. Chen. Side-Information based linear discriminant analysis for face recognition. BMVC, 2011.

[12] M. Kostinger, M. Hirzer, P. Wohlhart, P.M. Roth, H. Bischof. Large scale metric learning from equivalence constraints. CVPR, 2012.

[13] B. Moghaddam, T. Jebara and A Pentland. Bayesian face recognition. Pattern Recognition, 33: 1771–1782, 2000.

[14] H. V. Nguyen and L. Bai. Cosine similarity metric learning for face verification. ACCV, 2010.

[15] Y. Nesterov. Introductory Lectures on Convex Optimization: A Basic Course. Kluwer Academic Publisher, Boston, 2004.

[16] T. Ojala, M. Pietikainen and T. Maenpaa. Multiresolution gray-scale and rotation invariant texture classification with local binary patterns. IEEE Trans. PAMI, 24:971–987, 2002.

[17] P. Li, Y. Fu, U. Mohammed, J. Elder, and S. Prince. Probabilistic models for inference about identity. IEEE Trans. PAMI, 34(1): 144–157, 2012.

[18] N. Pinto and D. Cox. Beyond simple features: a largescale feature search approach to unconstrained face recognition. In International Conference on Automatic Face and Gesture Recognition, 2011.

[19] O. Shalit, D. Weinshall and G. Chechik. Online learning in the manifold of low-rank matrices. NIPS, 2010.

[20] Y. Taigman and L. Wolf and T. Hassner. Multiple one-shots for utilizing class label information. In BMVC, 2009.

[21] X. Wang and X. Tang. A unified framework for subspace face recognition. IEEE Trans. PAMI, 26 (9): 1222–1228, 2004.

[22] K. Q. Weinberger, J. Blitzer, and L. Saul. Distance metric learning for large margin nearest neighbour classification. NIPS, 2006.

[23] L. Wolf, T. Hassner and Y. Taigman. Similarity scores based on background samples. In ACCV, 2009.

[24] L. Wolf, T. Hassner and Y. Taigman. Descriptor based methods in the wild. In Real-Life Images workshop at the European Conference on Computer Vision, October, 2008.

[25] E. Xing, A. Ng, M. Jordan, and S. Russell. Distance metric learning with application to clustering with side information. NIPS, 2002.

[26] L. Yang and R. Jin. Distance metric learning: A comprehensive survey. In Technical report, Michigan State University, 2007.

[27] Y. Ying and P. Li. Distance metric learning with eigenvalue optimization. J. of Machine Learning Research, 13: 1–26, 2012. 22441155